Analyzing the effect of hyperparameters in a automobile classifier based on convolutional neural networks.
Elian Laura RiverosJose Galdos ChavezJuan C. Gutiérrez-CáceresPublished in: SCCC (2016)
Keyphrases
- hyperparameters
- convolutional neural networks
- model selection
- cross validation
- random sampling
- bayesian framework
- bayesian inference
- closed form
- gaussian processes
- prior information
- noise level
- gaussian process
- support vector
- maximum a posteriori
- em algorithm
- incremental learning
- regularization parameter
- convolutional network
- missing values
- parameter space
- computer vision
- data mining
- incomplete data
- maximum likelihood
- higher order
- pairwise
- sample size
- feature extraction